Efficient Optimized Spike Encoding of Multivariate Time-series
Dighanchal Banerjee, Sounak Dey, Arun M. George, Arijit Mukherjee · 2022
Spiking neural network (SNN) are emerging as a bio-plausible AI paradigm best suited for energy constrained edge use case. However the performance of SNNs largely depends upon the information content of the spike trains generated from real valued data by spike encoders - which are often found to be lossy. In this work, we have proposed a mutual information based optimisation technique of spike encoding to be used on multivariate time-series data. When tested using a spiking reservoir network, the technique is found to increase the network performance by upto 6% while performing classification task on different multivariate sensor data having variety of attributes.